Update tiny models for HrmTextForCausalLM

config.json

@@ -0,0 +1,39 @@
+{
+  "H_cycles": 2,
+  "L_bp_cycles": [
+    2
+  ],
+  "L_cycles": 3,
+  "architectures": [
+    "HrmTextForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 6,
+  "dtype": "float32",
+  "embedding_scale": 50.0,
+  "eos_token_id": 11,
+  "head_dim": 16,
+  "hidden_act": "gelu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_decoder": true,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "hrm_text",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 16,
+  "num_layers_per_stack": 2,
+  "pad_token_id": 5,
+  "prefix_lm": false,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 6,
+  "eos_token_id": 11,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 5,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff603a1d38f4ee6a2ad5bf9645f5975ee1497cfb8307b36b5ee3a52456c2a75d
+size 16910520

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|box_end|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}